© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 75692
    Prev
    Next
    INDEX
    Explanations

    programming and data science terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     TUESDAY
    -1.50
     will
    -1.44
    ございません
    -1.40
    $\$
    -1.39
    ५
    -1.37
    newblock
    -1.36
    віду
    -1.35
     capucha
    -1.33
     as
    -1.32
    iencies
    -1.31
    POSITIVE LOGITS
    ຣ
    1.46
     повече
    1.41
     each
    1.39
     nacionales
    1.36
    ENESS
    1.34
    咂
    1.34
    vård
    1.32
    чается
    1.32
     Jeden
    1.30
    ngày
    1.30
    Activations Density 0.087%

    No Known Activations